county-variant-detector
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill is focused on structural data analysis and diagnostic cataloging.- [PROMPT_INJECTION]: The skill processes untrusted HTML data via the html_content field, creating an indirect prompt injection surface. However, the implementation is limited to passive structural analysis and does not possess capabilities such as command execution or network access that could be leveraged by an attacker. No evidence of malicious exploitation was found.
- Ingestion points: html_content parameter in SKILL.md.
- Boundary markers: None.
- Capability inventory: Limited to structural extraction using BeautifulSoup; no dangerous tool access.
- Sanitization: Standard HTML parsing is used.
Audit Metadata